CN106019359A - Earthquake prediction system based on neural network - Google Patents
Earthquake prediction system based on neural network Download PDFInfo
- Publication number
- CN106019359A CN106019359A CN201610324909.1A CN201610324909A CN106019359A CN 106019359 A CN106019359 A CN 106019359A CN 201610324909 A CN201610324909 A CN 201610324909A CN 106019359 A CN106019359 A CN 106019359A
- Authority
- CN
- China
- Prior art keywords
- earthquake
- data
- training
- prediction apparatus
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title abstract description 5
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000007935 neutral effect Effects 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract 1
- 238000003475 lamination Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/01—Measuring or predicting earthquakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Emergency Alarm Devices (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides an earthquake prediction system based on a neural network, which belongs to the field of artificial intelligence. The data acquisition device mainly comprises a seismograph and a network module and is used for acquiring seismic waves and transmitting data through a network. The generation of the earthquake prediction device comprises the following steps: firstly, a large number of training sample sets are selected, mainly pictures about seismic waves. And then constructing a convolutional neural network system, training the convolutional neural network system by using training data, and generating a seismic prediction system after the training is finished. The monitoring alarm center mainly analyzes the output of the neural network and the data of the acquisition device to predict which position the earthquake will happen. The invention overcomes the defect of incomplete consideration of the characteristic matching algorithm through a general convolutional neural network model, has good generalization capability and improves the accuracy of prediction.
Description
Technical field
The present invention relates to artificial intelligence technology, particularly relate to a kind of Earthquake Forecast System based on neutral net.
Background technology
According to statistics, annual on the earth there is about ten thousand secondary earthquake more than 500, wherein the mankind can be caused the earthquake about more than 10 time of serious harm, but special violent earthquake always brings serious economic damage, casualties, brings serious burden to the psychology of people every time.
Present scientific and technological level cannot arrive by foreseeing earthquake accurately, is therefore badly in need of a kind of novel earthquake prediction apparatus.
Summary of the invention
Nowadays along with the rise of artificial intelligence neural networks so that machine oneself is abstract, study features is possibly realized.Therefore, the present invention proposes a kind of Earthquake Forecast System based on neutral net.By analyzing the data of earthquake for many years, allow machine that us can be helped to predict earthquake.
The solution of the present invention is as follows:
A kind of Earthquake Forecast System based on neutral net,
Mainly comprise data acquisition unit, earthquake prediction apparatus and monitoring alarm center；
Wherein
Data acquisition unit is mainly made up of seismic detector and mixed-media network modules mixed-media, for locality seismic wave and data is transmitted by network；Harvester can be distributed in national earthquake containing mixed-media network modules mixed-media and seismic detector, can be sent to earthquake prediction apparatus by the seismic wave information collected and positional information by network than place more frequently, harvester inside.
First earthquake prediction apparatus generates to comprise the steps of chooses substantial amounts of training sample set, primarily with regard to the picture of seismic wave；Then build convolutional neural networks system, and use training data that it is trained, after training completes, i.e. generate Earthquake Forecast System；
The output of monitoring alarm center Main Analysis neutral net and which position of data prediction of harvester will occur earthquake；
Data collecting system mainly gathers local seismic wave figure by seismic detector, and by network, this figure and positional information are dealt into earthquake prediction apparatus；
The probability that earthquake prediction apparatus analytically seismic wave images outputting earthquake occurs, and be sent to positional information and probabilistic information monitor alarm center.Monitoring alarm center obtains output and the positional information of earthquake prediction apparatus, is written into data base, and by giant-screen according to the descending display of Probability of Earthquake, if a certain location probability exceedes threshold value, reports to the police.
Wherein the generation of earthquake prediction apparatus, mainly comprises the steps of
(1) training sample is chosen, seismic wave picture when predominantly earthquake occurs and earthquake seismic wave picture when not occurring.
(2) building neural network model, select herein is convolutional neural networks, comprises an input layer, two convolutional layers, two sample level, a full articulamentum, an output layer.
(3) training neutral net, sends training sample into convolutional neural networks, and then constantly iteration is trained, and when the error rate of last output sample is less than intended value, deconditioning, network training completes, and generates earthquake prediction apparatus.
Beneficial effects of the present invention:
The present invention proposes a kind of Earthquake Forecast System based on neutral net, is widely used, easy and simple to handle, by novel artificial intelligence technology, the probability that real-time prediction earthquake can be facilitated to occur, has generalization ability strong, it is possible to the features such as self-teaching.
Accompanying drawing explanation
Fig. 1 is the composition frame chart of convolutional neural networks；
Fig. 2 is the simple flow chart of Earthquake Forecast System.
Detailed description of the invention
Below present disclosure is carried out more detailed elaboration:
Harvester can be distributed in national earthquake containing mixed-media network modules mixed-media and seismic detector, can be sent to earthquake prediction apparatus by the seismic wave information collected and positional information by network than place more frequently, harvester inside.
The generation of earthquake prediction apparatus is mainly by building convolutional neural networks, and is trained, and can be formed after training completes.Wherein convolutional neural networks comprises input layer, first volume lamination, the first sample level, volume Two lamination, the second sample level, full articulamentum, output layer etc..Seismic wave information picture input neural network when first will there is earthquake in a large number and during non-earthquake, through substantial amounts of iteration, neutral net reaches convergence, and hereafter, the data that can be collected by seismic detector input earthquake prediction apparatus in real time and obtain the probability that earthquake occurs.
Monitoring alarm center obtains output and the positional information of earthquake prediction apparatus, is written into data base, and by giant-screen according to the descending display of Probability of Earthquake, if a certain location probability exceedes threshold value, reports to the police.
Native system be embodied as step as shown in Figure 2:
First convolutional neural networks as shown in Figure 1 is built.Comprise input layer, first volume lamination, the first sub sampling layer, volume Two lamination, the second sub sampling layer, full articulamentum, output layer etc..
Wherein convolutional layer can comprise multiple convolution kernel (neuron), for extracting the different characteristic of input picture.And the output of convolutional layer is mainly sampled and is compressed by sub sampling layer.The results change of the second last sample level is become the vector of 1 dimension by full articulamentum, for representing the probability that earthquake occurs.
Seismic wave picture input convolutional neural networks when then a large amount of earthquakes being occurred or do not occurred, trains through successive ignition, if sample error is less than expection, completes training, generate earthquake prediction apparatus.
Secondly the seismic wave figure collected and positional information timing are sent to earthquake prediction apparatus by the harvester of distribution various places.Earthquake prediction apparatus analytically seismic wave picture, the probability that output earthquake occurs.
Output and positional information that finally earthquake prediction apparatus is produced by monitoring alarm center are stored in data base, by large screen display out, if the probability having earthquake to occur is more than threshold value, report to the police.
Claims (3)
1. an Earthquake Forecast System based on neutral net, it is characterised in that
Mainly comprise data acquisition unit, earthquake prediction apparatus and monitoring alarm center；
Wherein
Data acquisition unit is mainly made up of seismic detector and mixed-media network modules mixed-media, for locality seismic wave and data is transmitted by network；
First earthquake prediction apparatus generates to comprise the steps of chooses substantial amounts of training sample set, primarily with regard to the picture of seismic wave；Then build convolutional neural networks system, and use training data that it is trained, after training completes, i.e. generate Earthquake Forecast System；
The output of monitoring alarm center Main Analysis neutral net and which position of data prediction of harvester will occur earthquake；
Data collecting system mainly gathers local seismic wave figure by seismic detector, and by network, this figure and positional information are dealt into earthquake prediction apparatus；
The probability that earthquake prediction apparatus analytically seismic wave images outputting earthquake occurs, and be sent to positional information and probabilistic information monitor alarm center,
Monitoring alarm center monitors earthquake probability of happening data in real time, when probability exceedes threshold value, reports to the police.
Earthquake Forecast System the most according to claim 1, it is characterised in that
Mainly comprise the steps of
(1) training sample is chosen, seismic wave picture when predominantly earthquake occurs and earthquake seismic wave picture when not occurring；
(2) building neural network model, what the present invention selected is convolutional neural networks, comprises an input layer, two convolutional layers, two sample level, a full articulamentum, an output layer；
(3) training neutral net, sends training sample into convolutional neural networks, and then constantly iteration is trained, and when the error rate of last output sample is less than intended value, deconditioning, network training completes, and generates earthquake prediction apparatus.
Earthquake Forecast System the most according to claim 2, it is characterised in that
Monitoring alarm center obtains output and the positional information of earthquake prediction apparatus, is written into data base, and by giant-screen according to the descending display of Probability of Earthquake, if a certain location probability exceedes threshold value, reports to the police.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610324909.1A CN106019359A (en) | 2016-05-17 | 2016-05-17 | Earthquake prediction system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610324909.1A CN106019359A (en) | 2016-05-17 | 2016-05-17 | Earthquake prediction system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106019359A true CN106019359A (en) | 2016-10-12 |
Family
ID=57098396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610324909.1A Pending CN106019359A (en) | 2016-05-17 | 2016-05-17 | Earthquake prediction system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106019359A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971230A (en) * | 2017-05-10 | 2017-07-21 | 中国石油大学(北京) | First break pickup method and device based on deep learning |
| CN108897614A (en) * | 2018-05-25 | 2018-11-27 | 福建天晴数码有限公司 | A kind of memory method for early warning and server-side based on convolutional neural networks |
| CN109118001A (en) * | 2018-08-09 | 2019-01-01 | 成都天地量子科技有限公司 | A kind of mountain fire monitoring method and system based on satellite remote sensing date |
| CN110082822A (en) * | 2019-04-09 | 2019-08-02 | 中国科学技术大学 | The method for carrying out earthquake detection using convolutional neural networks |
| CN110334567A (en) * | 2019-03-22 | 2019-10-15 | 长江大学 | A kind of microseism useful signal detection method |
| CN110609320A (en) * | 2019-08-28 | 2019-12-24 | 电子科技大学 | Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion |
| CN113253336A (en) * | 2021-07-02 | 2021-08-13 | 深圳市翩翩科技有限公司 | Earthquake prediction method and system based on deep learning |
| EP3889652A1 (en) * | 2020-03-30 | 2021-10-06 | Qingdao University Of Technology | Performance-level seismic motion hazard analysis method based on three-layer dataset neural network |
| US11143770B1 (en) | 2020-05-28 | 2021-10-12 | Massachusetts Institute Of Technology | System and method for providing real-time prediction and mitigation of seismically-induced effects in complex systems |
| CN113534238A (en) * | 2020-04-18 | 2021-10-22 | 中国石油化工股份有限公司 | System and method for data acquisition and data mining in seismic data processing process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1571982A (en) * | 2002-03-26 | 2005-01-26 | 科学与工业研究会 | Improved performance of artificial neural network model in the presence of instrumental noise and measurement error |
| JP2010025877A (en) * | 2008-07-24 | 2010-02-04 | Citizen Holdings Co Ltd | Earthquake alarm device |
| CN102610092A (en) * | 2012-03-23 | 2012-07-25 | 天津大学 | Urban road speed predication method based on RBF (radial basis function) neural network |
| CN104573731A (en) * | 2015-02-06 | 2015-04-29 | 厦门大学 | Rapid target detection method based on convolutional neural network |
| CN204496013U (en) * | 2015-03-11 | 2015-07-22 | 山东大学 | Active source 3-D seismics advance geology exploration device in rock tunnel(ling) machine |
-
2016
- 2016-05-17 CN CN201610324909.1A patent/CN106019359A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1571982A (en) * | 2002-03-26 | 2005-01-26 | 科学与工业研究会 | Improved performance of artificial neural network model in the presence of instrumental noise and measurement error |
| JP2010025877A (en) * | 2008-07-24 | 2010-02-04 | Citizen Holdings Co Ltd | Earthquake alarm device |
| CN102610092A (en) * | 2012-03-23 | 2012-07-25 | 天津大学 | Urban road speed predication method based on RBF (radial basis function) neural network |
| CN104573731A (en) * | 2015-02-06 | 2015-04-29 | 厦门大学 | Rapid target detection method based on convolutional neural network |
| CN204496013U (en) * | 2015-03-11 | 2015-07-22 | 山东大学 | Active source 3-D seismics advance geology exploration device in rock tunnel(ling) machine |
Non-Patent Citations (2)
| Title |
|---|
| 卢溜等: "卷积神经网络在地震多属性分析中的应用", 《中国地球科学联合学术年会》 * |
| 江汶乡: "面向地震预警的强震动数据处理技术研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971230A (en) * | 2017-05-10 | 2017-07-21 | 中国石油大学(北京) | First break pickup method and device based on deep learning |
| CN108897614A (en) * | 2018-05-25 | 2018-11-27 | 福建天晴数码有限公司 | A kind of memory method for early warning and server-side based on convolutional neural networks |
| CN109118001A (en) * | 2018-08-09 | 2019-01-01 | 成都天地量子科技有限公司 | A kind of mountain fire monitoring method and system based on satellite remote sensing date |
| CN110334567A (en) * | 2019-03-22 | 2019-10-15 | 长江大学 | A kind of microseism useful signal detection method |
| CN110082822B (en) * | 2019-04-09 | 2020-07-28 | 中国科学技术大学 | Method for detecting earthquake by using convolution neural network |
| CN110082822A (en) * | 2019-04-09 | 2019-08-02 | 中国科学技术大学 | The method for carrying out earthquake detection using convolutional neural networks |
| CN110609320A (en) * | 2019-08-28 | 2019-12-24 | 电子科技大学 | Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion |
| EP3889652A1 (en) * | 2020-03-30 | 2021-10-06 | Qingdao University Of Technology | Performance-level seismic motion hazard analysis method based on three-layer dataset neural network |
| CN113534238A (en) * | 2020-04-18 | 2021-10-22 | 中国石油化工股份有限公司 | System and method for data acquisition and data mining in seismic data processing process |
| CN113534238B (en) * | 2020-04-18 | 2024-03-29 | 中国石油化工股份有限公司 | System and method for data acquisition and data mining in seismic data processing process |
| US11143770B1 (en) | 2020-05-28 | 2021-10-12 | Massachusetts Institute Of Technology | System and method for providing real-time prediction and mitigation of seismically-induced effects in complex systems |
| WO2021242289A1 (en) * | 2020-05-28 | 2021-12-02 | Massachusetts Institute Of Technology | System and method for providing real-time prediction and mitigation of seismically-induced effects in complex systems |
| CN113253336A (en) * | 2021-07-02 | 2021-08-13 | 深圳市翩翩科技有限公司 | Earthquake prediction method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106019359A (en) | Earthquake prediction system based on neural network | |
| Kong et al. | Machine learning in seismology: Turning data into insights | |
| CN108364097B (en) | Based on the typhoon cloud system prediction technique for generating confrontation network | |
| Guha-Sapir et al. | Estimating populations affected by disasters: A review of methodological issues and research gaps | |
| CN101515200B (en) | Target selecting method based on transient visual evoked electroencephalogram | |
| Dabaghi | Stochastic modeling and simulation of near-fault ground motions for performance-based earthquake engineering | |
| CN103761537B (en) | Image classification method based on low-rank optimization feature dictionary model | |
| CN110361778A (en) | A kind of Reconstruction of seismic data method based on generation confrontation network | |
| WO2023035923A1 (en) | Video checking method and apparatus and electronic device | |
| CN111738044B (en) | Campus violence assessment method based on deep learning behavior recognition | |
| Lombardi et al. | The assumption of Poisson seismic-rate variability in CSEP/RELM experiments | |
| CN113052147A (en) | Behavior identification method and device | |
| Zhang et al. | Urban spatial risk prediction and optimization analysis of POI based on deep learning from the perspective of an epidemic | |
| Pollino et al. | Collaborative open source geospatial tools and maps supporting the response planning to disastrous earthquake events | |
| Monrat et al. | A belief rule based flood risk assessment expert system using real time sensor data streaming | |
| Zuccolo et al. | Comparing the performance of regional earthquake early warning algorithms in Europe | |
| Tasakos et al. | Deep learning-based anomaly detection in nuclear reactor cores | |
| Naguit et al. | From source to building fragility: post-event assessment of the 2013 M7. 1 Bohol, Philippines, Earthquake | |
| CN116186561B (en) | Running gesture recognition and correction method and system based on high-dimensional time sequence diagram network | |
| CN111224938A (en) | Wireless seismograph network compressed data transmission method | |
| CN113222206B (en) | Traffic state prediction method based on ResLS-C deep learning combination | |
| Li et al. | Structural health monitoring response reconstruction based on UAGAN under structural condition variations with few-shot learning [J] | |
| CN116363474A (en) | Relay protection device detection method and system based on space-time attention mechanism CNN | |
| CN109784602A (en) | A kind of disaster-ridden kind of coupling physical vulnerability assessment method based on PTVA model | |
| Rubin | Efficient and automatic wireless geohazard monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161012 |